INDEX

Explanations

specific technical or scientific terminology related to research or experiments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gg

-0.60

 mantel

-0.57

 Marav

-0.57

 Metro

-0.52

ave

-0.50

zend

-0.49

com

-0.47

WindowSize

-0.46

ken

-0.46

 Mote

-0.46

POSITIVE LOGITS

Autoritní

0.86

 Lightboxes

0.83

tagHelperRunner

0.70

mbggenerated

0.70

 propOrder

0.69

WriteTagHelper

0.67

Билгалдахарш

0.66

GeoNames

0.65

Geplaatst

0.63

 intStringLen

0.62

Activations Density 0.569%

specific technical or scientific terminology related to research or experiments

No Comments

No Known Activations